Cover Image

Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Xiyang, Tian, Yuanhe, Wang, Hongzhi, Song, Yan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
by: Zhang, Yuanhe, et al.
Published: (2025)

DNAZEN: Enhanced Gene Sequence Representations via Mixed Granularities of Coding Units
by: Mao, Lei, et al.
Published: (2025)

Gradient Harmonization in Unsupervised Domain Adaptation
by: Huang, Fuxiang, et al.
Published: (2024)

Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
by: Wang, Shaoqi, et al.
Published: (2024)

Diffusion Models for Time Series Forecasting: A Survey
by: Su, Chen, et al.
Published: (2025)

Autonomous Source Knowledge Selection in Multi-Domain Adaptation
by: Li, Keqiuyin, et al.
Published: (2025)

HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
by: Wang, Yiding, et al.
Published: (2025)

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training
by: Lu, Yishun, et al.
Published: (2025)

Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference
by: Hu, Pengfei, et al.
Published: (2026)

ONG: Orthogonal Natural Gradient Descent
by: Yadav, Yajat, et al.
Published: (2025)

Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain
by: Qiu, Zhongxi, et al.
Published: (2025)

Adaptive Data Selection for Multi-Layer Perceptron Training: A Sub-linear Value-Driven Method
by: Zhang, Xiyang, et al.
Published: (2025)

GIO: Gradient Information Optimization for Training Dataset Selection
by: Everaert, Dante, et al.
Published: (2023)

Context-Aware Self-Adaptation for Domain Generalization
by: Yan, Hao, et al.
Published: (2025)

3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection
by: Ding, Hongxin, et al.
Published: (2024)

Gradient-Congruity Guided Federated Sparse Training
by: Tian, Chris Xing, et al.
Published: (2024)

Selection of LLM Fine-Tuning Data based on Orthogonal Rules
by: Li, Xiaomin, et al.
Published: (2024)

Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
by: Hu, Yuelin, et al.
Published: (2026)

ROOT: Robust Orthogonalized Optimizer for Neural Network Training
by: He, Wei, et al.
Published: (2025)

Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training
by: Cui, Peng, et al.
Published: (2026)

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
by: Zhao, Yang, et al.
Published: (2026)

Fisher-Orthogonal Projected Natural Gradient Descent for Continual Learning
by: Garg, Ishir, et al.
Published: (2026)

Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
by: Song, Jingze, et al.
Published: (2026)

Orthogonal Factor-Based Biclustering Algorithm (BCBOF) for High-Dimensional Data and Its Application in Stock Trend Prediction
by: Huang, Yan, et al.
Published: (2025)

Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
by: Lin, Luxi, et al.
Published: (2026)

Generalizing to New Dynamical Systems via Frequency Domain Adaptation
by: Qin, Tiexin, et al.
Published: (2025)

Rethinking Propagation for Unsupervised Graph Domain Adaptation
by: Liu, Meihan, et al.
Published: (2024)

Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
by: Chen, Wei, et al.
Published: (2026)

Enhancing few-shot time series forecasting with LLM-guided diffusion
by: Shi, Haonan, et al.
Published: (2026)

GAIN: Multiplicative Modulation for Domain Adaptation
by: Yao, Hengshuai, et al.
Published: (2026)

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs
by: Wang, Zige, et al.
Published: (2025)

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
by: Zhang, Zhen, et al.
Published: (2024)

A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
by: Song, Yu, et al.
Published: (2025)

ColA: Collaborative Adaptation with Gradient Learning
by: Diao, Enmao, et al.
Published: (2024)

Continual Domain Adversarial Adaptation via Double-Head Discriminators
by: Shen, Yan, et al.
Published: (2024)

Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training
by: Lin, Jinhong, et al.
Published: (2026)

Efficient Ensembles Improve Training Data Attribution
by: Deng, Junwei, et al.
Published: (2024)

Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
by: Choi, Youngjun, et al.
Published: (2025)

Harnessing Orthogonality to Train Low-Rank Neural Networks
by: Coquelin, Daniel, et al.
Published: (2024)

Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching
by: Miao, Tianhao, et al.
Published: (2026)